基于转移神经网络的中文AMR解析

抽象语义表示(abstract meaning representation,AMR)是一种领域无关的句子语义表示方法,它将一个句子的语义抽象为一个单根有向无环图,AMR解析旨在将句子解析为对应的AMR图。目前,中文AMR研究仍然处于起步阶段。该文结合中文AMR特性,采用基于转移神经网络的方法对中文AMR解析问题展开了试验性研究。首先,实现了一个基于转移解码方法的增量式中文AMR解析神经网络基线系统;然后,通过引入依存路径语义关系表示学习和上下文相关词语语义表示学习,丰富了特征的表示;最后,模型中应用序列化标注的模型实现AMR概念识别,优化了AMR概念识别效果。实验结果表明,该模型在中文AMR解析任务中达到了0.61的Smatch F1值,明显优于基线系统。

Chinese AMR Parsing using Transition-based Neural Network

Abstract Meaning Representation (AMR) is a domain-independent sentence semantic representation method, which abstracts the semantics of a sentence into a single directed acyclic graph. AMR parsing aims at parsing sentences into corresponding AMR graphs. In this paper, a tentative study of Chinese AMR parsing is conducted based on Chinese AMR features and the transition-based neural network. An incremental Chinese AMR parsing baseline strategy utilizing transition-based decoding method is proposed. Then, semantic representation of dependency paths and context information are utilized to improve the proposed model. Finally, the concept recognition in AMR parsing is conducted by applying sequence labeling. Experiments demonstrate that the proposed model outperforms the baseline by yielding Smatch F1 of 0.61 on Chinese AMR Parsing.